| Component | vLLM |
| Severity | medium (CVSS 5.9) |
| CVSS vector | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H |
| Published (NVD) | 2026-10-05 |
| Last modified | 2026-10-06 |
| Affected versions | < 0.30.0 read from the advisory text: NVD has not published CPE data yet |
| Fixed in | 0.30.0 |
| Weakness | CWE-400 |
| CISA KEV | not listed |
NVD description
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker can send unique arbitrary method tokens to unguarded routes such as /tokenize, causing Prometheus's Family::get_or_create function to permanently create counter and histogram label sets. Those label sets increase process memory usage and enlarge the /metrics response until the service or monitoring path is exhausted. This issue is fixed in version 0.30.0.
What to do
- Upgrade vLLM to
0.30.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-105759
- https://github.com/vllm-project/vllm/commit/3735c2d5f5248259482b9045c34fb7a8a3892352
- https://github.com/vllm-project/vllm/pull/56058
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0
- https://github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48
Read more
Other vLLM CVEs
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser he...
A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file v...
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/mo...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/r...
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a m...